English

Testing Bayesian Networks

Data Structures and Algorithms 2020-01-28 v2 Information Theory Machine Learning math.IT Statistics Theory Statistics Theory

Abstract

This work initiates a systematic investigation of testing high-dimensional structured distributions by focusing on testing Bayesian networks -- the prototypical family of directed graphical models. A Bayesian network is defined by a directed acyclic graph, where we associate a random variable with each node. The value at any particular node is conditionally independent of all the other non-descendant nodes once its parents are fixed. Specifically, we study the properties of identity testing and closeness testing of Bayesian networks. Our main contribution is the first non-trivial efficient testing algorithms for these problems and corresponding information-theoretic lower bounds. For a wide range of parameter settings, our testing algorithms have sample complexity sublinear in the dimension and are sample-optimal, up to constant factors.

Keywords

Cite

@article{arxiv.1612.03156,
  title  = {Testing Bayesian Networks},
  author = {Clement Canonne and Ilias Diakonikolas and Daniel Kane and Alistair Stewart},
  journal= {arXiv preprint arXiv:1612.03156},
  year   = {2020}
}

Comments

To appear in IEEE Transactions on Information Theory